A talking avatar from your script
A script in, a talking avatar video with a lip synced AI voice out.
Cloned or picked voice
The avatar speaks your script with a lip synced AI voice: your cloned voice, or one you pick.
Burned in captions
Subtitles are burned in, so a clip works on mute.
No watermark
No watermark on any plan, and you own what you generate on every plan.
Create faster with AI
Automate the tedious parts of production and focus on the story.
TemplateReady madeSmart Templates
Jumpstart your creativity with ready made templates for marketing, education, social media, and internal comms.
Captions burned inAuto Captions
Generate subtitles for your videos and burn them in, so a clip works on mute. Improve accessibility and engagement instantly.
On Brand by Prompt
Describe your colours, setting and style in the prompt, or start from your own image with image to video, so each clip matches what you already publish.
Image to video
One credit balance34 Text to Video Models
Sora 2, Veo 3, Kling, Seedance, Hailuo, LTX-2 and Pika on one credit balance, plus image, voice and music models for the rest of the video.
Every model and what it costs
Marketing
Start your next marketing video from a ready made template.
Education
Start your next lesson from a ready made template.
Social media
Start your next social post from a ready made template.
Internal comms
Start your next team update from a ready made template.
From script to final cut
No camera needed and no experience required.
- Step 1
Write the script
Type what your avatar should say.
- Step 2
Lip syncPick an avatar and a voice
A stock avatar or your own, with your cloned voice or one you pick.
- Step 3
Download the MP4
Lip synced, with captions burned in and no watermark.
Every model and what it costs
Avatars to star in your video, and every video model priced.
Stock avatars
Need an avatar to star in your video? Explore our library of stock avatars or create your own.
View Stock AvatarsMulti shot video in seconds
A 5, 10 or 15 second video from a prompt, cutting between shots you describe. From 20 credits.
How it worksA 30 to 60 second video from one prompt
Made in 10 second parts and joined, at 3 credits a second.
How it worksText to video
Open text to videoQuestions, answered
Is there a watermark on the output?
No. Percify does not apply a watermark to output on any plan, and you own what you generate on every plan. Paid plans differ by how many credits they carry, not by watermarking or licensing.
Why does my AI video look different every time I generate it?
Because text to video has nothing to anchor to. The model invents the subject, the motion and the scene together, so the same prompt run twice returns different people and places. If the subject has to stay the same between shots, start from an image instead: image to video keeps the person in the photo fixed and generates motion around them.
Why doesn't the generated video match my prompt?
Usually because the prompt describes a style rather than a scene. Prompts like “cinematic” or “professional” give the model no subject, framing or motion to work from, and it fills the gaps itself. Name the shot instead: who is in frame, how they are framed, what moves, and how it is lit. The more of the scene you specify, the less the model invents.
Why does the subject drift or distort in longer clips?
Generated motion accumulates error over time, so the opening seconds hold together better than the end. Faces and hands show it first because small distortions are most visible there. Generate in shorter segments and join them rather than asking for one long take, and frame tighter so there is less for the model to invent.
Can I collaborate with my team?
Percify does not have per seat accounts today; a plan is one login, so a team shares one account and its credits.
What export formats are supported?
Videos download as MP4. Resolution depends on the model: talking videos render at up to 720p, and each text and image to video model shows its own resolutions before you run it.
